Papers by Young-Kil Kim
Data Augmentation by Data Noising for Open-vocabulary Slots in Spoken Language Understanding (N19-3)
Copied to clipboard
| Challenge: | Neural networks are used to understand spoken language understanding (SLU) but it is difficult to recognize the slots of unknown words or ‘open-vocabulary’ slots because of the high cost of creating a manually tagged SLU dataset. |
| Approach: | They propose to use a recurrent neural network to nois slots for data augmentation by using an attention-based bi-directional recurrence neural network. |
| Outcome: | The proposed method achieves performance improvements of up to 0.57% and 3.25 in intent prediction (accuracy) and slot filling (f1-score) and 0.53% accuracy. |
Improving a Multi-Source Neural Machine Translation Model with Corpus Extension for Low-Resource Languages (L18-1)
Copied to clipboard
| Challenge: | In machine translation, we often try to collect resources to improve performance. |
| Approach: | They propose to use synthetic methods to extend low-resource corpus to create target sentences using synthetic methods. |
| Outcome: | The proposed method improves translation performance for low-resource language pairs. |